Kudu Native RDD

Spark与Kudu的集成同事提供了kudu RDD

import org.apache.kudu.spark.kudu.KuduContext

import org.apache.spark.{SparkConf, SparkContext}

import org.apache.spark.sql.{Row, SparkSession}

/**

  * Created by angel；

  */

object KuduNativeRDD {

  def main(args: Array[String]): Unit = {

    val sparkConf = new SparkConf().setAppName("AcctfileProcess")

      //设置Master_IP并设置spark参数

      .setMaster("local")

      .set("spark.worker.timeout", "500")

      .set("spark.cores.max", "10")

      .set("spark.rpc.askTimeout", "600s")

      .set("spark.network.timeout", "600s")

      .set("spark.task.maxFailures", "1")

      .set("spark.speculationfalse", "false")

      .set("spark.driver.allowMultipleContexts", "true")

      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")

    val sparkContext = SparkContext.getOrCreate(sparkConf)

    val sqlContext = SparkSession.builder().config(sparkConf).getOrCreate().sqlContext

    //使用spark创建kudu表

    val kuduMasters = "hadoop01:7051,hadoop02:7051,hadoop03:7051"

    val kuduContext = new KuduContext(kuduMasters, sqlContext.sparkContext)

    //TODO 1：定义kudu表

    val kuduTableName = "spark_kudu_tbl"

    //TODO 2：指定想要的列

    val kuduTableProjColumns = Seq("name", "age")

    //TODO 3：读取表，将数据转换成rdd

    val custRDD = kuduContext.kuduRDD(sparkContext, kuduTableName, kuduTableProjColumns)

    //TODO 4：将rdd数据转换成tuple

    val custTuple = custRDD.map {

      case Row(name: String, age: Int) => (name, age)

    }

    //TODO 5：打印

    custTuple.collect().foreach(println(_))

  }

}